Merge remote-tracking branch 'upstream/main' into eval_div

yuanx749 · yuanx749 · commit 1173c5436505 · 2024-10-03T22:48:07.000+08:00
diff --git a/.github/workflows/code-checks.yml b/.github/workflows/code-checks.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
 
 env:
   ENV_FILE: environment.yml
diff --git a/.github/workflows/docbuild-and-upload.yml b/.github/workflows/docbuild-and-upload.yml
@@ -4,13 +4,13 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
 
 env:
   ENV_FILE: environment.yml
diff --git a/.github/workflows/package-checks.yml b/.github/workflows/package-checks.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     types: [ labeled, opened, synchronize, reopened ]
 
 permissions:
diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     paths-ignore:
       - "doc/**"
       - "web/**"
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -652,6 +652,7 @@ Plotting
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
 - Bug in :meth:`.DataFrameGroupBy.__len__` and :meth:`.SeriesGroupBy.__len__` would raise when the grouping contained NA values and ``dropna=False`` (:issue:`58644`)
+- Bug in :meth:`.DataFrameGroupBy.any` that returned True for groups where all Timedelta values are NaT. (:issue:`59712`)
 - Bug in :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupby.groups` that would not respect groupby argument ``dropna`` (:issue:`55919`)
 - Bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
diff --git a/pandas/_libs/include/pandas/datetime/date_conversions.h b/pandas/_libs/include/pandas/datetime/date_conversions.h
@@ -9,6 +9,7 @@ The full license is in the LICENSE file, distributed with this software.
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
+
 #include <numpy/ndarraytypes.h>
 
 // Scales value inplace from nanosecond resolution to unit resolution
diff --git a/pandas/_libs/include/pandas/parser/io.h b/pandas/_libs/include/pandas/parser/io.h
@@ -10,9 +10,10 @@ The full license is in the LICENSE file, distributed with this software.
 #pragma once
 
 #define PY_SSIZE_T_CLEAN
-#include "tokenizer.h"
 #include <Python.h>
 
+#include "tokenizer.h"
+
 #define FS(source) ((file_source *)source)
 
 typedef struct _rd_source {
diff --git a/pandas/_libs/include/pandas/parser/pd_parser.h b/pandas/_libs/include/pandas/parser/pd_parser.h
@@ -13,9 +13,10 @@ extern "C" {
 #endif
 
 #define PY_SSIZE_T_CLEAN
-#include "pandas/parser/tokenizer.h"
 #include <Python.h>
 
+#include "pandas/parser/tokenizer.h"
+
 typedef struct {
   int (*to_double)(char *, double *, char, char, int *);
   int (*floatify)(PyObject *, double *, int *);
diff --git a/pandas/_libs/include/pandas/vendored/klib/khash_python.h b/pandas/_libs/include/pandas/vendored/klib/khash_python.h
@@ -3,6 +3,7 @@
 #pragma once
 
 #include <Python.h>
+
 #include <pymem.h>
 #include <string.h>
 
diff --git a/pandas/_libs/src/vendored/ujson/python/JSONtoObj.c b/pandas/_libs/src/vendored/ujson/python/JSONtoObj.c
@@ -38,11 +38,10 @@ Numeric decoder derived from TCL library
 
 // Licence at LICENSES/ULTRAJSON_LICENSE
 
-// clang-format off
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
+
 #include "pandas/vendored/ujson/lib/ultrajson.h"
-// clang-format on
 
 static int Object_objectAddKey(void *Py_UNUSED(prv), JSOBJ obj, JSOBJ name,
                                JSOBJ value) {
diff --git a/pandas/_libs/src/vendored/ujson/python/ujson.c b/pandas/_libs/src/vendored/ujson/python/ujson.c
@@ -40,6 +40,7 @@ Numeric decoder derived from TCL library
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
+
 #define PY_ARRAY_UNIQUE_SYMBOL UJSON_NUMPY
 #include "numpy/arrayobject.h"
 
diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py
@@ -371,6 +371,10 @@ def _call_cython_op(
 
         is_datetimelike = dtype.kind in "mM"
 
+        if self.how in ["any", "all"]:
+            if mask is None:
+                mask = isna(values)
+
         if is_datetimelike:
             values = values.view("int64")
             is_numeric = True
@@ -380,12 +384,10 @@ def _call_cython_op(
             values = values.astype(np.float32)
 
         if self.how in ["any", "all"]:
-            if mask is None:
-                mask = isna(values)
             if dtype == object:
                 if kwargs["skipna"]:
                     # GH#37501: don't raise on pd.NA when skipna=True
-                    if mask.any():
+                    if mask is not None and mask.any():
                         # mask on original values computed separately
                         values = values.copy()
                         values[mask] = True
diff --git a/pandas/core/shared_docs.py b/pandas/core/shared_docs.py
@@ -65,9 +65,9 @@
     Determine which axis to align the comparison on.
 
     * 0, or 'index' : Resulting differences are stacked vertically
-        with rows drawn alternately from self and other.
+      with rows drawn alternately from self and other.
     * 1, or 'columns' : Resulting differences are aligned horizontally
-        with columns drawn alternately from self and other.
+      with columns drawn alternately from self and other.
 
 keep_shape : bool, default False
     If true, all rows and columns are kept.
diff --git a/pandas/tests/groupby/test_grouping.py b/pandas/tests/groupby/test_grouping.py
@@ -1180,3 +1180,15 @@ def test_grouping_by_key_is_in_axis():
     result = gb.sum()
     expected = DataFrame({"a": [1, 2], "b": [1, 2], "c": [7, 5]})
     tm.assert_frame_equal(result, expected)
+
+
+def test_groupby_any_with_timedelta():
+    # GH#59712
+    df = DataFrame({"value": [pd.Timedelta(1), pd.NaT]})
+
+    result = df.groupby(np.array([0, 1], dtype=np.int64))["value"].any()
+
+    expected = Series({0: True, 1: False}, name="value", dtype=bool)
+    expected.index = expected.index.astype(np.int64)
+
+    tm.assert_series_equal(result, expected)
